SOTAVerified

Automatic Speech Recognition (ASR)

Automatic Speech Recognition (ASR) involves converting spoken language into written text. It is designed to transcribe spoken words into text in real-time, allowing people to communicate with computers, mobile devices, and other technology using their voice. The goal of Automatic Speech Recognition is to accurately transcribe speech, taking into account variations in accent, pronunciation, and speaking style, as well as background noise and other factors that can affect speech quality.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2551–2600 of 3012 papers

TitleStatusHype
Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers—0
Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learning—0
Advancing CTC-CRF Based End-to-End Speech Recognition with Wordpieces and Conformers—0
Advancing Hearing Assessment: An ASR-Based Frequency-Specific Speech Test for Diagnosing Presbycusis—0
Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy—0
Advancing Multi-talker ASR Performance with Large Language Models—0
Advancing Speech Recognition With No Speech Or With Noisy Speech—0
Adversarial Attacks and Defenses for Speech Recognition Systems—0
Adversarial Attacks on ASR Systems: An Overview—0
Adversarial Black-Box Attacks on Automatic Speech Recognition Systems using Multi-Objective Evolutionary Optimization—0
Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition—0
Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition—0
Adversarial Speaker Adaptation—0
Adversarial Speaker Disentanglement Using Unannotated External Data for Self-supervised Representation Based Voice Conversion—0
Adversarial synthesis based data-augmentation for code-switched spoken language identification—0
Adversarial Training for Multilingual Acoustic Modeling—0
Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model—0
Advocating Character Error Rate for Multilingual ASR Evaluation—0
Affect Recognition in Conversations Using Large Language Models—0
A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding—0
AfriNames: Most ASR models "butcher" African Names—0
AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR—0
Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond—0
AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition—0
A GEN AI Framework for Medical Note Generation—0
A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks—0
A Generative Model of a Pronunciation Lexicon for Hindi—0
A Genetic Programming Approach To Zero-Shot Neural Architecture Ranking—0
Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning—0
A Hardware-Oriented and Memory-Efficient Method for CTC Decoding—0
A Hierarchical Neural Model for Learning Sequences of Dialogue Acts—0
A Hierarchical Reasoning Graph Neural Network for The Automatic Scoring of Answer Transcriptions in Video Job Interviews—0
A higher order Minkowski loss for improved prediction ability of acoustic model in ASR—0
A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition—0
Ain't Misbehavin' -- Using LLMs to Generate Expressive Robot Behavior in Conversations with the Tabletop Robot Haru—0
Bonseyes AI Pipeline -- bringing AI to you. End-to-end integration of data, algorithms and deployment tools—0
A Joint Model of Orthography and Morphological Segmentation—0
A Language Agnostic Multilingual Streaming On-Device ASR System—0
A Lexical-aware Non-autoregressive Transformer-based ASR Model—0
Algorithms For Automatic Accentuation And Transcription Of Russian Texts In Speech Recognition Systems—0
A light-weight and efficient punctuation and word casing prediction model for on-device streaming ASR—0
A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems—0
Aligning Pre-trained Models for Spoken Language Translation—0
Aligning Speech to Languages to Enhance Code-switching Speech Recognition—0
Alignment Entropy Regularization—0
Alignment-Free Training for Transducer-based Multi-Talker ASR—0
Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognition—0
Alignment Restricted Streaming Recurrent Neural Network Transducer—0
Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework—0
Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation—0
Show:102550
← PrevPage 52 of 61Next →
All datasetsLRS2RealMANSagaleeHUI speech corpusLRS3-TEDM-AILabs speech datasetThe Spoken Wikipedia CorporaVoxforge GermanVoxPopuli

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TM-CTCTest WER10.1—Unverified
2TM-seq2seqTest WER9.7—Unverified
3CTC/attentionTest WER8.2—Unverified
4LF-MMI TDNNTest WER6.7—Unverified
5Whisper-LLaMATest WER6.6—Unverified
6End2end ConformerTest WER3.9—Unverified
7End2end ConformerTest WER3.7—Unverified
8MoCo + wav2vec (w/o extLM)Test WER2.7—Unverified
9CTC/AttentionTest WER1.5—Unverified
10WhisperTest WER1.3—Unverified
#ModelMetricClaimedVerifiedStatus
1SpatialNetCER14.5—Unverified
2CleanMel-L-maskCER14.4—Unverified
#ModelMetricClaimedVerifiedStatus
1ConformerTest WER15.32—Unverified
2Whisper-largev3-finetunedTest WER10.82—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)1.89—Unverified
#ModelMetricClaimedVerifiedStatus
1DistillAVWER1.4—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)4.28—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)8.04—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)3.36—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer Transducer (German)WER (%)8.98—Unverified